INDEX

Explanations

food-related words, specifically related to meals

oai_token-act-pair · gpt-3.5-turbo

references to meals or food-related concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idency

-0.74

ioxide

-0.74

ignty

-0.72

 bluff

-0.71

itars

-0.67

Jed

-0.65

 Morse

-0.64

 Moff

-0.63

ados

-0.62

orporated

-0.61

POSITIVE LOGITS

worms

1.25

 meal

1.13

 meals

1.10

 Meal

1.05

mares

0.99

 buffet

0.98

 eaten

0.97

worm

0.93

cloth

0.87

 cooked

0.84

Activations Density 0.019%

food-related words, specifically related to meals

references to meals or food-related concepts

No Comments

No Known Activations